Triple

T12567203
Position Surface form Disambiguated ID Type / Status
Subject John Lavery E295501 entity
Predicate workLocation P7 FINISHED
Object Tangier E44467 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Tangier | Statement: [John Lavery, workLocation, Tangier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tangier
Context triple: [John Lavery, workLocation, Tangier]
  • A. Tangier chosen
    Tangier is a historic Moroccan port city on the Strait of Gibraltar known for its blend of North African, European, and Middle Eastern influences and its long-standing role as a cultural crossroads.
  • B. Agadir
    Agadir is a major coastal city in southwestern Morocco known for its Atlantic beaches, modern resort infrastructure, and role as a key tourist destination.
  • C. Nador
    Nador is a town in northern Algeria, likely situated within the coastal Tipaza Province west of Algiers.
  • D. Nador
    Nador is a coastal city in northeastern Morocco known as an important commercial and fishing port on the Mediterranean.
  • E. El Aaiún
    El Aaiún is the largest city and de facto administrative center of Western Sahara, located near the Atlantic coast in the disputed territory controlled by Morocco.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d6ad9cac2c81908e8a7bed82d1e21d completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d954a325948190994bcfc9d571a3a8 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f655914f908190afbebbec3cb57e73 completed May 2, 2026, 7:50 p.m.
Created at: April 8, 2026, 11:49 p.m.